Subscribe

UiPath Document Understanding

UiPath Document Understanding

Create & Configure Fields

Fields cannot be renamed, so please think carefully before naming a field. If, however, there are fields that you later decide you do not want to use for training an ML model, you can either delete them or you can always hide them using the Hidden checkbox in the Edit field window.

📘

Note:

A maximum of 300 fields can be created.

Column Fields

A line item Description or Unit Price on an invoice document would be examples of Column fields.

Create a new Column Field


  1. Click create_fieldcreate_field in the table section at the top of the page to add a new Column field. The Create Column Field window is displayed.
  2. Fill in a unique name for the field in the Enter unique field name field. The field does not accept uppercase letters. It can only contain lowercase letters, numbers, underscore _ and dash -.
  3. Click Create. The Edit Field window is displayed.
  4. From the Content Type drop-down, select the content type.
  5. From the Scoring drop-down, select the measure used to determine accuracy when running evaluations of model predictions.
  6. Click the Hotkey field and press a key on your keyboard to automatically populate it.
  7. Fill in the hex code of the desired field color on the Color field.
  8. Select the Split items checkbox if you want this field to be used as a delimiter between line items or rows in a table. Any line on which this field appears is considered to be a new line item or row in the table. Most commonly this is used on Line Amount fields on Invoice line items.
  9. Select the Hidden checkbox if you do not want this field to be part of exported datasets.
  10. Click Save to save your settings.

Edit a Column Field


Click the Edit field edit_fieldedit_field button. The available options for column fields can be found in the table below.

Option

Description

Content type

The content type of a field:
string: appropriate for company names or addresses, as well as payment terms, or for any other field where the RPA developer prefers to build the parsing or formatting logic manually, in the RPA workflow.
number: appropriate for amounts or quantities, with intelligent parsing of the decimal/thousands separators.
date: the model parses, formats and unifies the output in a yyyy-mm-dd format.
phone: appropriate for phone numbers. Formatting removes letters and parentheses, and replaces spaces with dashes.
id-no: appropriate for alphanumeric codes, numbers of IDs, it is similar to the string content type, but includes cleaning of any characters coming before a colon :. If the id number you need to extract might contain colon : characters, please use string as content type instead to avoid data loss.

Shortcut

The shortcut key for the field. One or two keys allowed.

Color

The color for the field in hex format. If the value is not valid, a new one is generated.

Scoring

The measure used to determine accuracy when running evaluations of model predictions. It can only be configured for string content type. All other content types use an Exact Match scoring strategy. Options:
exact match: a prediction is only deemed to be correct (score of 1) if it exactly matches the true value. If it differs by even a single character, then it is deemed to be incorrect (score of 0).
levenshtein: a prediction is deemed to be partially correct according to the Levenshtein distance between the prediction and the true value. If a 10-letter value is predicted correctly, except for the last 2 characters, then the score of that prediction will be 0.8.

Split items

Select this checkbox if you want this field to be used as a delimiter between line items or rows in a table. Any line on which this field appears is considered to be a new line item or row in the table. Most commonly, this is used on Line Amount fields on Invoice line items.

Hidden

Select this checkbox if you do not want this field to be part of exported datasets.

Delete a Column Field


To delete a column field, follow these steps:

  1. Click the Edit field edit_fieldedit_field button corresponding to the column field you want to delete.
  2. Click the Delete button.
  3. Type the exact name of the field.




  4. Click OK.
  5. The column field and its associated labeled data is deleted.

Regular Fields

These are fields which appear only once on a given document. A line item Invoice Number or Total Amount on an invoice document would be examples of Column fields.

Create a new Regular Field


  1. Click create_fieldcreate_field on the right pane in the Regular Fields section. The Create Regular Field window is displayed.
  2. Fill in a unique name for the field in the Enter unique field name field. The field does not accept uppercase letters. It can only contain lowercase letters, numbers, underscore _ and dash -.
  3. Click Create. The Edit Field window is displayed.
  4. Select the content type from the Content Type drop-down.
  5. Select the post processing mechanism in case the model predicts more than one instance of a field on a given page from the Post processing drop-down.
  6. Click the Hotkey field and press a key on your keyboard to automatically populate it.
  7. In the Color field, fill in the hex code of the desired field color o
  8. From the Multi page drop-down, select the data retrieval strategy. This option is used in case that fields appear on a few different pages of a multi-page document. This option defines how the model decides which one to return.
  9. From the Scoring drop-down, select the measure used to determine accuracy when running evaluations of model predictions.
  10. Select the Multi line checkbox if the field to be checked against might span across multiple text lines, such as addresses or descriptions. If this option is not selected, only the first line is returned.
  11. Select the Hidden checkbox if you do not want this field to be part of exported datasets.
  12. Click Save to save your settings.

Edit a Regular Field


Click the Edit field edit_fieldedit_field button. The available options for regular fields can be found in the table below.

Option

Regular Field

Content type

The content type of a field:
string: appropriate for company names or addresses, as well as payment terms, or for any other field where the RPA developer prefers to build the parsing or formatting logic manually, in the RPA workflow.
number: appropriate for amounts or quantities, with intelligent parsing of the decimal/thousands separators.
date: the model parses, formats and unifies the output in a yyyy-mm-dd format.
phone: appropriate for phone numbers. Formatting removes letters and parentheses, and replaces spaces with dashes.
id-no: appropriate for alphanumeric codes, numbers of IDs, it is similar to the string content type, but includes cleaning of any characters coming before a colon :. If the id number you need to extract might contain colon : characters, please use string as content type instead to avoid data loss.

Post processing

The post-processing mechanism. If the model predicts more than one instance of a field on a given page, the model returns:
highest_confidence: the value with the highest confidence.
first_span: the first value.
largest_value: the largest numeric value. This is only displayed for number content type and is appropriate for Total Amount fields.
longest_value: the value consisting of the largest number of characters.

Shortcut

The shortcut key for the field. One or two keys allowed.

Color

The color for the field in hex format. If the value is not valid, a new one is generated.

Multi page

The data return strategy in case a field appears on different pages of a multipage document.
highest_confidence - the default choice for string, phone, and number content types.
first_occurrence - the default choice for id-no and date content types.
last_occurrence
longest_string
shortest_string
highest_num_value - only displayed for number content type.
lowest_num_value - only displayed for number content type.

Scoring

The measure used to determine accuracy when running evaluations of model predictions. It can only be configured for string content type. All other content types use an Exact Match scoring strategy. Options:
exact match: a prediction is only deemed to be correct (score of 1) if it exactly matches the true value. If it differs by even a single character, then it is deemed to be incorrect (score of 0).
levenshtein: a prediction is deemed to be partially correct according to the Levenshtein distance between the prediction and the true value. If a 10-letter value is predicted correctly, except for the last 2 characters, then the score of that prediction will be 0.8.

Multi line

Select this checkbox for fields which may span across multiple text lines (addresses or descriptions), otherwise, only the first line is returned.

Hidden

Select this checkbox if you do not want this field to be part of exported datasets.

Delete a Regular Field


To delete a regular field, follow these steps:

  1. Click the Edit field edit_fieldedit_field button corresponding to the regular field you want to delete.
  2. Click the Delete button.
  3. Type the exact name of the field.




  4. Click OK.
  5. The regular field and its associated labeled data is deleted.

Classification Fields

Data points which refer to a document as a whole. For instance, the Expense Type of a receipt (Food, Hotel, Airline, Transportation) or the Currency of an invoice (USD, EUR, JPY) would be examples of Classification fields.

Create a new Classification Field


  1. Click create_fieldcreate_field on the right pane in the Classification Fields section. The Create Classification Field window is displayed.
  2. Fill in a unique name for the field in the Enter unique field name field. The field does not accept uppercase letters. It can only contain lowercase letters, numbers, underscore _ and dash -.
  3. Click Create. The Edit Field window is displayed.
  4. In the text area, fill in the list of classes and type the names as a comma separated list.
  5. Click Save to save your settings.

🚧

Classification fields are not retrained

Contrary to Regular and Column fields, Classification fields are not Re-trained. For example for Currency field, if you retrain the Invoices model on a dataset containing only USD and INR invoices, then the resulting model is only able to recognize those two currencies.

Edit a Classification Field


Click the Edit field edit_fieldedit_field button. Define a list of possible values. Commas must separate values. An optional description of the value may be included after colon : (option 1 : description 1).

Delete a Classification Field


To delete a classification field, follow these steps:

  1. Click the Edit field edit_fieldedit_field button corresponding to the classification field you want to delete.
  2. Click the Delete button.
  3. Type the exact name of the field.




  4. Click OK.
  5. The classification field and its associated labeled data is deleted.

Updated 15 days ago


Create & Configure Fields


Suggested Edits are limited on API Reference Pages

You can only suggest edits to Markdown body content, but not to the API spec.